Andy (Jianan) Zhao
I am currently a third-year PhD candidate in Computer Science at Mila and the University of
Montreal, supervised by Prof. Jian Tang. Before
embarking on my PhD journey, I completed my MSc in Computer Science at Beijing University of
Posts and Telecommunications, under the guidance of Prof.
Chuan Shi. I am passionate about developing simple yet effective methods and primarily
focus my research on graph machine learning and natural language processing.
Email  / 
Github  / 
Google Scholar / 
Twitter
|
|
Selected Publications
(* stands for equal contribution)
|
GraphAny: A Foundation Model for Node Classification on Any Graph
Jianan Zhao,
Hesham Mostafa,
Mikhail Galkin,
Michael Bronstein,
Zhaocheng Zhu,
Jian Tang
The first foundation model for node classification that generalizes to any graph with arbitrary feature and label spaces.
GraphAny surpasses supervised baselines (e.g. GCN, GAT) in an inductive (training-free) manner.
Arxiv Preprint, 2024
[paper]
[code]
[blog]
|
GraphText: Graph Reasoning in Text Space
Jianan Zhao,
Le Zhuo,
Yikang Shen,
Meng Qu,
Kai Liu,
Michael Bronstein,
Zhaocheng Zhu,
Jian Tang
GraphText enables training-free and interactive
graph reasoning using LLMs.
Arxiv Preprint, 2023
[paper]
[code]
|
Learning on Large-scale Text-attributed Graphs via Variational Inference
Jianan Zhao*,
Meng Qu*,
Chaozhuo Li,
Hao Yan,
Qian Liu,
Rui Li,
Xing Xie,
Jian Tang
[ICLR'23 Notable-top5% (Oral)] International
Conference on Learning Representations
Top 1 accuracy of three datasets on the
Open Graph Benchmark.
[paper]
[code]
|
HousE: Knowledge Graph Embedding with Householder Parameterization
Rui Li,
Jianan Zhao,
Chaozhuo Li,
Di He,
Yiqi Wang,
Yuming Liu, Hao Sun, Senzhang Wang, Weiwei Deng,
Yanming Shen,
Xing Xie,
Qi Zhang
[ICML'22] The International Conference of Machine Learning
[paper]
[code]
|
Self-Supervised Graph Structure Refinement for Graph Neural Networks
Jianan Zhao*,
Qianlong Wen*,
Mingxuan Ju,
Chuxu Zhang,
Yanfang Ye
[WSDM'23] : ACM International Conference on Web Search and Data Mining
[paper]
[code]
|
Adaptive Kernel Graph Neural Network
Mingxuan Ju,
Shifu Hou,
Yujie Fan,
Jianan Zhao,
Liang Zhao,
Yanfang Ye
[AAAI'22] AAAI Conference on Artificial Intelligence
[paper]
[code]
|
Gophormer: Ego-Graph Transformer for Node Classification
Jianan Zhao*,
Rui Li*,
Qianlong Wen*,
Chaozhuo Li,
Yiqi Wang,
Yuming Liu,
Hao Sun,
Yanfang Ye,
Xing Xie
Arxiv Preprint, 2021
[paper]
[code]
|
RxNet: Rx-refill Graph Neural Network for Overprescribing Detection
Jianfei Zhang,
Ai-Te Kuo,
Jianan Zhao,
Qianlong Wen,
Erin Winstanley,
Chuxu Zhang,
Yanfang Ye
[CIKM'21] ACM International Conference on Information and Knowledge Management
Best Full-Paper Award [1/1251]
[paper]
|
Multi-View Self-Supervised Heterogeneous Graph Embedding
Jianan Zhao*,
Qianlong Wen*,
Shiyu Sun,
Yanfang Ye,
Chuxu Zhang
[ECML/PKDD'21] European Conference on Machine Learning and Principles and Practice of
Knowledge Discovery in Databases
[paper]
[code]
|
Heterogeneous Graph Structure Learning for Graph Neural Networks
Jianan Zhao*,
Xiao Wang*,
Chuan Shi,
Binbin Hu,
Guojie Song,
Yanfang Ye
[AAAI'21] AAAI Conference on Artificial Intelligence
[paper]
[code]
|
Network Schema Preserving Heterogeneous Information Network Embedding
Jianan Zhao*,
Xiao Wang*,
Chuan Shi,
Zekuan Liu,
Yanfang Ye
[IJCAI'20] International Joint Conference on Artificial Intelligence
[paper]
[code]
|
Recent News
- [1 Nov 2023] Invited by Data Skeptic to give a
podcast talk.
- [6 Oct 2023] Proposed GraphText: a
framework for training-free and interactive graph reasoning using LLMs. Notably, GraphText-ChatGPT outperforms
several
supervised-GNN baselines, like GCNII and GATv2, without any training on graph. Special
thanks to Michael Bronstein for advising.
- [20 Jan 2023] Our GLEM paper,
merging graph neural networks with language models, was recognized in the top 5%
at ICLR 2023. GLEM topped the charts on the OGB Leaderboard in
several categories.
- [8 Sep 2022] Earned the Stars of Tomorrow [Top 10%] certificate at my
Microsoft Research Asia internship (Jul 2021 - Jul 2022). Gratitude to mentor Chaozhuo
Li and group leader Xing Xie.
- [16 May 2022] Delighted to announce our paper on HousE: Knowledge Graph Embedding with
Householder Parameterization has been accepted at ICML2022. Both paper and code are
now available.
- [11 Feb 2021] Our paper "RxNet: Rx-refill Graph Neural Network for Overprescribing
Detection"
paper clinched the Best
Full Paper Award at CIKM2021!
- [26 Oct 2021] Released our new work on Gophormer,
a graph transformer for node-level tasks.
- [24 Oct 2021] Proudly co-founded the MLNLP Student
Community (China) as a committee member.
- [26 Jul 2021] Our work NSHE work is now featured in DGL
0.7.
|
More About Me!
Life is an extraordinary journey, and I am deeply committed to enriching both my mind and
body. On the mental front, I enjoy reading and listen to podcasts on neuroscience and general life.
Physically, I am passionate about bouldering/climbing, powerlifting, and making a splash in
the pool.
As I navigate through my academic journey, I aim to accomplish more than just research.
Here are some fun facts about me:
🎸 Guitar: I play fingerstyle guitar and founded the first intern guitar
club at Microsoft Research Asia (Dec 2021).
🏋️ Powerlifting: Reached Top 4%
lifter by squatting 2.5x body weight
(200kg/80kg RM3) on July 12, 2023.
🧗 Bouldering: I'm keen in bouldering and aiming at achieving V8 at some
day. Check out my climbing clips here.
By pursuing these goals alongside my research work, I manage strive 🤣 to live a
balanced life.
|
|